一种改进的SUSAN算子棋盘格角点亚像素检测算法

摘要

SUSAN算子在检测角点时,只以USAN区域面积的大小作为判断准则,忽略USAN区域形状的影响.因此,该算法对棋盘格标定板中的内角点与边缘点难以区分.针对此问题,本文提出在SUSAN圆模板内再次采用SUSAN算子来实现对棋盘格标定板角点的有效检测.此外,在每个初定位角点的局部邻域内,采用二次曲面拟合法得到角点的亚像素坐标.实验证明,所提出的算法准确、有效、适应性好,能为摄像机标定提供亚像素精度的角点信息.%One of the disadvantages of the SUSAN operator is that it just takes into account USAN' s size without considering US-AN's shape in detecting feature points. It's difficult to distinguish the chessboard comers and edge points for the SUSAN algorithm. Therefore another SUSAN circular mask is added within the SUSAN circular mask to overcome this defect. Moreover, sub-pixel coordinates corners are calculated with quadric surface fitting. Experimental results show that the proposed algorithm has high precision and can provide reliable data for high-precision camera calibration.